const output = await replicate.run(
  "zhouhaojiang/qwen_32b:94378aca5cdf8fb28951d729424b636737017abc9eb9e843bd710ff4169db012",
  {
    input: {
      top_k: 100,
      top_p: 1,
      prompt: "你爱我吗",
      max_tokens: 1024,
      temperature: 1,
      system_prompt: ""
    }
  }
);

console.log(output);

output = replicate.run(
    "zhouhaojiang/qwen_32b:94378aca5cdf8fb28951d729424b636737017abc9eb9e843bd710ff4169db012",
    input={
        "top_k": 100,
        "top_p": 1,
        "prompt": "你爱我吗",
        "max_tokens": 1024,
        "temperature": 1,
        "system_prompt": ""
    }
)

# The zhouhaojiang/qwen_32b model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/zhouhaojiang/qwen_32b/api#output-schema
    print(item, end="")

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "zhouhaojiang/qwen_32b:94378aca5cdf8fb28951d729424b636737017abc9eb9e843bd710ff4169db012",
    "input": {
      "top_k": 100,
      "top_p": 1,
      "prompt": "你爱我吗",
      "max_tokens": 1024,
      "temperature": 1,
      "system_prompt": ""
    }
  }' \
  https://api.replicate.com/v1/predictions